consciousness/src/llm.rs

147 lines
5 KiB
Rust
Raw Normal View History

// LLM utilities: model invocation and response parsing
//
// Calls claude CLI as a subprocess. Uses prctl(PR_SET_PDEATHSIG)
// so child processes die when the daemon exits, preventing orphans.
use crate::store::Store;
use regex::Regex;
use std::fs;
use std::os::unix::process::CommandExt;
use std::process::Command;
fn log_usage(agent: &str, model: &str, prompt: &str, response: &str,
duration_ms: u128, ok: bool) {
let dir = crate::config::get().data_dir.join("llm-logs").join(agent);
let _ = fs::create_dir_all(&dir);
let date = chrono::Local::now().format("%Y-%m-%d");
let path = dir.join(format!("{}.md", date));
let ts = chrono::Local::now().format("%H:%M:%S");
let status = if ok { "ok" } else { "ERROR" };
let entry = format!(
"\n## {} — {} ({}, {:.1}s, {})\n\n\
### Prompt ({} chars)\n\n\
```\n{}\n```\n\n\
### Response ({} chars)\n\n\
```\n{}\n```\n\n---\n",
ts, agent, model, duration_ms as f64 / 1000.0, status,
prompt.len(), prompt,
response.len(), response,
);
use std::io::Write;
if let Ok(mut f) = fs::OpenOptions::new().create(true).append(true).open(&path) {
let _ = f.write_all(entry.as_bytes());
}
}
/// Call a model via claude CLI. Returns the response text.
///
/// Sets PR_SET_PDEATHSIG on the child so it gets SIGTERM if the
/// parent daemon exits — no more orphaned claude processes.
fn call_model(agent: &str, model: &str, prompt: &str) -> Result<String, String> {
// Write prompt to temp file (claude CLI needs file input for large prompts)
let tmp = std::env::temp_dir().join(format!("poc-llm-{}-{:?}.txt",
std::process::id(), std::thread::current().id()));
fs::write(&tmp, prompt)
.map_err(|e| format!("write temp prompt: {}", e))?;
let mut cmd = Command::new("claude");
cmd.args(["-p", "--model", model, "--tools", "", "--no-session-persistence"])
.stdin(fs::File::open(&tmp).map_err(|e| format!("open temp: {}", e))?)
.env_remove("CLAUDECODE");
// Use separate OAuth credentials for agent work if configured
if let Some(ref dir) = crate::config::get().agent_config_dir {
cmd.env("CLAUDE_CONFIG_DIR", dir);
}
// Tell hooks this is a daemon agent call, not interactive
cmd.env("POC_AGENT", "1");
let start = std::time::Instant::now();
let result = unsafe {
cmd.pre_exec(|| {
libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM);
Ok(())
})
.output()
};
fs::remove_file(&tmp).ok();
match result {
Ok(output) => {
let elapsed = start.elapsed().as_millis();
if output.status.success() {
let response = String::from_utf8_lossy(&output.stdout).trim().to_string();
log_usage(agent, model, prompt, &response, elapsed, true);
Ok(response)
} else {
let stderr = String::from_utf8_lossy(&output.stderr);
let preview: String = stderr.chars().take(500).collect();
log_usage(agent, model, prompt, &preview, elapsed, false);
Err(format!("claude exited {}: {}", output.status, preview.trim()))
}
}
Err(e) => Err(format!("spawn claude: {}", e)),
}
}
/// Call Sonnet via claude CLI.
pub(crate) fn call_sonnet(agent: &str, prompt: &str) -> Result<String, String> {
call_model(agent, "sonnet", prompt)
}
/// Call Haiku via claude CLI (cheaper, faster — good for high-volume extraction).
pub(crate) fn call_haiku(agent: &str, prompt: &str) -> Result<String, String> {
call_model(agent, "haiku", prompt)
}
/// Parse a JSON response, handling markdown fences.
pub(crate) fn parse_json_response(response: &str) -> Result<serde_json::Value, String> {
let cleaned = response.trim();
let cleaned = cleaned.strip_prefix("```json").unwrap_or(cleaned);
let cleaned = cleaned.strip_prefix("```").unwrap_or(cleaned);
let cleaned = cleaned.strip_suffix("```").unwrap_or(cleaned);
let cleaned = cleaned.trim();
if let Ok(v) = serde_json::from_str(cleaned) {
return Ok(v);
}
// Try to find JSON object or array
let re_obj = Regex::new(r"\{[\s\S]*\}").unwrap();
let re_arr = Regex::new(r"\[[\s\S]*\]").unwrap();
if let Some(m) = re_obj.find(cleaned) {
if let Ok(v) = serde_json::from_str(m.as_str()) {
return Ok(v);
}
}
if let Some(m) = re_arr.find(cleaned) {
if let Ok(v) = serde_json::from_str(m.as_str()) {
return Ok(v);
}
}
let preview: String = cleaned.chars().take(200).collect();
Err(format!("no valid JSON in response: {preview}..."))
}
/// Get non-operational keys for prompt context.
pub(crate) fn semantic_keys(store: &Store) -> Vec<String> {
let skip = ["MEMORY", "where-am-i", "work-queue", "work-state"];
let mut keys: Vec<String> = store.nodes.keys()
.filter(|k| !skip.contains(&k.as_str()))
.cloned()
.collect();
keys.sort();
keys.truncate(200);
keys
}